Noometry

Model comparison

Claude 3 Opus vs Llama 3-8B

Claude 3 Opus is the stronger model overall, scoring 29.5 to 25.5 on the Noometry Index.

Last verified . 30 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude 3 Opus scores higher in 8 categories and Llama 3-8B in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Opus leads 24.5 to 7.8.
  • The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 6.1% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusLlama 3-8B
ProviderAnthropicMeta
Noometry Index29.525.5
Released2024-02-292024-04-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4634

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude 3 Opus leads

Claude 3 Opus: 32.9 (#267), Llama 3-8B: 31.0 (#289)

BenchmarkClaude 3 OpusLlama 3-8B
BigCodeBench Instruct45.5%31.9%
LMArena Coding12641152
BigCodeBench Complete57.4%36.9%
HumanEval+77.4%56.7%
MBPP+73.3%54.8%
WeirdML19.2%—
LiveBench Coding38.6%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Llama 3-8B: —

BenchmarkClaude 3 OpusLlama 3-8B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Too close to call

Claude 3 Opus: 14.6 (#324), Llama 3-8B: 14.3 (#326)

BenchmarkClaude 3 OpusLlama 3-8B
Chess Puzzles5%0%
LMArena Hard Prompts12451133
DTBench61.6%43.9%
Epoch Capabilities Index126.91116.45
ForecastBench58.458.6
WinoGrande88.5%75.7%
SimpleBench23.5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Adversarial NLI—57.3%
LiveBench49.2%—

Math Claude 3 Opus leads

Claude 3 Opus: 14.8 (#299), Llama 3-8B: 8.8 (#323)

BenchmarkClaude 3 OpusLlama 3-8B
OTIS Mock AIME 2024-20254.7%1.9%
LMArena Math12731151
MATH Level 537.5%6.1%
LiveBench Math43.6%—

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Llama 3-8B: 7.8 (#308)

BenchmarkClaude 3 OpusLlama 3-8B
GPQA Diamond47.2%26.1%
LMArena Expert12231113
MMLU84.6%68.8%
SimpleQA Verified12.6%—
Confabulations22.7%—
ARC (AI2) Challenge—82.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Llama 3-8B: —

BenchmarkClaude 3 OpusLlama 3-8B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Llama 3-8B: 30.8 (#261)

BenchmarkClaude 3 OpusLlama 3-8B
LMArena Non-English12581098
LMArena Chinese12481076
LMArena French12751159
LMArena German12581104
LMArena Japanese1204967
LMArena Korean11871004
LMArena Russian12801109
LMArena Spanish12461173

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Llama 3-8B: 58.4 (#260)

BenchmarkClaude 3 OpusLlama 3-8B
LMArena Instruction Following12481127
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Llama 3-8B: 34.2 (#251)

BenchmarkClaude 3 OpusLlama 3-8B
LMArena Longer Query12591128

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Llama 3-8B: 37.5 (#256)

BenchmarkClaude 3 OpusLlama 3-8B
LMArena Text12621166
LMArena Creative Writing12351150
LMArena Multi-Turn12751152
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Llama 3-8B?

Claude 3 Opus is the stronger model overall, scoring 29.5 to 25.5 on the Noometry Index.

Is Claude 3 Opus or Llama 3-8B better for coding?

Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 31.0 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Llama 3-8B share?

30 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper